Estimation Methods

Back to top

Basic Estimation Method

The Marine Recreational Information Program (MRIP) produces catch and effort estimates using information from three complementary surveys:

  • The mail-based Fishing Effort Survey (FES) is sent to randomly selected fishing households in coastal states on the Atlantic and Gulf coasts. Recipients of the mail survey are asked how many trips they took in the preceding two months and data collected are f used to estimate the total number of shore and private boat angler trips (effort).

  • The For-Hire Survey (FHS) is a telephone survey of for-hire boat operators that is used to monitor charter and head/party boat fishing activity to estimate the total number of charter/headboat angler trips (effort). Additionally, the Southeast Region Headboat Survey monitors recreational headboat catch and effort in the south Atlantic and Gulf of Mexico.

  • The Access Point Angler Intercept Survey (APAIS) is a survey at fishing/marina sites that monitors the catch rates of fishing participants in the shore, private boat, and charter boat modes. The APAIS collects data that are used to estimate catch by species per angler fishing trip. Trained interviewers conduct in person interviews with anglers to determine the number and sizes of fish caught, and other trip related information. In the Northeast, headboat catch rates are determined from observations of at-sea samplers who monitor catch aboard sampled headboat trips.

We calculate effort using FES and FHS, and trip catch rates using APAIS. The effort estimate can be used to expand the mean catch rate to get an estimate of the total number of fish caught.

Effort x Catch Rate = Total Catch

For example, if 5 people made 3 trips each (15 angler trips total) and averaged 1 black sea bass and 2 cod per trip, we would estimate their total catch to be:

15 angler trips x 1 black sea bass per trip = 15 black sea bass

15 angler trips x 2 cod per trip = 30 cod

We produce estimates for every species, every mode of fishing, and three different catch types:

  • Type A catch estimates are based on fish brought back to the dock that are observed and identified by trained interviewers.

  • Type B1 catch estimates are based on reported fish that were used for bait, released dead, or filleted (i.e., fish that are killed and identification is by individual anglers, not samplers).

  • Type B2 catch estimates are based on reported fish that were released alive (again, identification is by individual anglers).

This is the most fundamental approach to estimating total catch, but it is usually necessary to adjust the effort estimates produced by the FES and FHS. For example, the FES only samples households in coastal states and therefore does not reach people in inland states. We use information from the onsite APAIS survey, where we ask what state a person is from, to adjust the state level estimates accordingly. The FHS charter angler trip estimates are adjusted to account for angler fishing trips made on charter boats not coverd in that voluntary survey.

Back to top

Example: Basic Estimation with Effort Adjustment

NOTE: Prior to January 2018, we estimated effort for shore and private boat anglers using the Coastal Household Telephone Survey (CHTS). We are in the process of revising the complete data series, which will be released in July 2018. Although the example below uses CHTS data, the estimation process is the same.

The following table is an example of the various survey components that are used to generate catch estimates for private boat mode in Massachusetts. Use the numbers in the table below to estimate catch following these steps:

  1. Start with the original estimated private boat mode effort for Massachusetts from the CHTS for 2-month sample intervals Waves 3 (May–June), 4 (July–August), and 5 (September–October) for the years 2011, 2012, and 2013.

  2. Calculate the coverage adjustment factor (“Adjustment” on the table—accounts for people who could not be surveyed) for that wave, and multiply it by the original effort to get an adjusted effort estimate.

  3. Calculate the weighted mean catch per angler trip (“Catch Per Effort” on the table) from the APAIS survey (for private boat mode, in this case).

  4. Multiply the adjusted effort estimate of angler trips by the catch per trip estimate to obtain the catch estimate.

Massachusetts Private Boat Mode Example¹

Year

2011

2011

2011

2012

2012

2012

2013

2013

2013

Wave

3 4 5 3 4 5 3 4 5

Original Effort²

237,114 392,138 301,444 359,247 562,259 133,695 333,813 503,932 365,785
Adjustment 1.3688 1.3162 1.3104 1.3794 1.3646 1.3634 1.4499 1.3306 1.1763
Adjusted Effort 324,558 516,118 395,008 495,548 767,233 182,279 484,010 670,539 430,270
                   
A Catch Per Effort 0.0070 0.0024 0 0.0226 0 0.0122 0.0739 0.0153 0.1212
B1 Catch Per Effort 0.2315 0.0687 0.0511 0.5350 0.0101 0.3058 0.0616 0.0569 0.0443
B2 Catch Per Effort 0.4513 0.1671 0.1164 0.8452 0.2625 0.6488 0.3519 0.8898 0.5697
                   
A Catch Estimate 2,270 1,228 0 11,214 0 2,232 35,769 10,275 52,139
B1 Catch Estimate 75,127 35,477 20,201 265,101 7,774 55,745 29,816 38,185 19,065
B2 Catch Estimate 146,481 86,245 45,988 418,828 201,393 118,257 170,333 596,664 2

¹ Due to rounding error, if you calculate the estimates above, you won't get exactly the same numbers shown.

² Prior to January 2018, we estimated effort for shore and private boat anglers using the Coastal Household Telephone Survey (CHTS). We are in the process of revising the complete data series, which will be released in July 2018. The chart above represents CHTS data,  but the estimation process is the same.

Back to top

Weighted Estimation Method

In the basic estimation example, we obtained a weighted estimate of the mean catch per angler trip from the APAIS data. Survey weights provide more accurate estimates because they account for the fact that some people and sites are more likely than others to participate in interviews. For basic weighting, if a given sample unit had a 1/10 chance of being selected, the assigned weight would be the inverse of that probability, or 10/1 = 10. In the APAIS, there are multiple stages of sample selection that require weighting.

Primary stage weights: The first sampling unit for the APAIS is a specific fishing site and time interval. The probability of selection for a given site-time combination depends on how active the fishing site is expected to be during the time interval, as predicted from historical information. For example, let's say that we have three types of fishing sites and their expected activity levels during an assigned time interval for interviewing (the following numbers are for illustrative purposes only and do not represent actual numbers used in our survey estimates):

L for low activity level, expected to have about 10 angler trips

M for medium activity level, expected to have about 40 angler trips

H for high activity level, expected to have about 100 angler trips

Let's say for a given area we have 40 L-sites, 20 M-sites, and 8 H-sites. Based on the known activity levels, the probability of selection for each site is:

Activity level / (L * L-sites + M * M-sites + H * H-sites) = Probability of being selected for a given site-time combination

L-sites: 10 / (10 * 40 + 40 * 20 + 100 * 8) = 1/200 chance of being selected

M-sites: 40 / (10 * 40 + 40 * 20 + 100 * 8) = 1/50 chance of being selected

H-sites: 100 / (10 * 40 + 40 * 20 + 100 * 8) = 1/20 chance of being selected

Now, let's say we take a small sample of 5 site-days and end up selecting 1 L-site, 2 M-sites, and 2 H-sites. The site weights are the inverse of the selection probabilities, so in this example the primary stage weights would be 200 for L-sites, 50 for M-sites, and 20 for H-sites.

Secondary stage weights: When visiting an assigned site in an assigned time interval, each APAIS interviewer tries to interview as many anglers who have completed fishing for the day as he/she can while keeping track of how many total trips were completed at the site. For the lower activity sites, it may be easy to interview every angler trip, while at the higher activity sites, people may be leaving at the same time and the interviewer may not be able to interview every angler. For each assignment, we calculate a second stage selection probability and create a weight for each interview that is based on the inverse of that probability.

Working with our example:

At the L-sites, there were 10 trips as expected and all 10 were interviewed, so the probability is 10/10, or 1, and the weight is also 1.

At the M-sites, there were 40 trips, but only 32 were interviewed, so the probability is 32/40, or 4/5, and the weight is 5/4 = 1.25.

At the H-sites, there were 100 trips, but only 40 were interviewed, so the probability is 40/100, or 2/5, and the weight is 5/2 = 2.5.

Combining weights: The overall weights assigned to each trip can then be calculated by multiplying the site-time selection (primary stage) weight by the trip selection (secondary stage) weight. The overall weights assigned to each trip in our example are:

L-sites: 200 * 1 = 200

M-sites: 50 * 1.25 = 62.5

H-sites: 20 * 2.5 = 50

Calculating catch per unit effort: To calculate the weighted catch per unit effort for a particular species, we first calculate the weighted catch estimate by multiplying the number of fish caught by the respective trip weight and then summing these values. To continue with our example, let's say that we're interested in species X. At the L-site that was selected, a total of 6 fish of species X were caught among the 10 interviewed trips. Across the selected M-sites, a total of 30 fish of species X were caught among the 64 total interviewed trips. Across the selected H-sites, a total of 34 fish of species X were caught among the 80 total interviewed trips. In this case, the weighted catch estimates are:

L-sites: 6 * 200 = 1,200

M-sites: 30 * 62.5 = 1,875

H-sites: 34 * 50 = 1,700

Sum: 1,200 + 1,875 + 1,700 = 4,775  

To calculate the weighted catch per unit effort, we then need to divide this weighted catch estimate sum by the total sum of the weights. We can calculate that by multiplying the combined weights by the total number of interviewed trips for a particular site. In this example, the sum of the weights would be (10 * 200) + (64 * 62.5) + (80 * 50) = 10,000. Therefore, the weighted mean catch per angler trip would be 4,775 / 10,000 = 0.4775.

The "unweighted" mean catch per angler trip could be calculated by taking the total number of fish caught and dividing by the total number of interviewed trips; in this example, it would be 70 / 154 = 0.4545. However, this is a biased estimate of the actual catch per unit effort because it doesn't reflect the sampling design. This may not look like a large numerical difference from the weighted estimate, but the difference could be much larger for other examples.

Back to top

Example: Weighted Estimation

The table below shows the weighted estimation example described above, demonstrating each step in calculating weighted estimates.

Numerical Weighting Example
Site Type L M H Total Notes
Number of Sites 40 20 8 68  
Expected Trips per Site 10 40 100    
Total Expected Trips 400 800 800 2000  
Probability of Selection 1/200 1/50 1/20    
Site Weight 200 50 20   Inverse of probability of selection
#of Trips at Each Site 10 40 100    
# of Interview Trips/Site 10 32 40   Average trips interviewed per site
Probability of Selection 10/10 32/40 40/100   Interviewed trips/Total trips
Interview Weight 1 1.25 2.5   Inverse of probability of selection
Overall Trip Weight 200 62.5 50   Site weight x Interview weight
           
Total Trips Across Sites 10 80 200 290  
Total Interviewed Trips 10 64 80 154  
Total # of Species X Caught 6 30 34 70  
           
Weighted Catch of Species X 1,200 1,875 1,700 4,775  
Sum of Weights 2,000 4,000 4,000 10,000 Sum of interviewed trips x weights
Weighted Catch per Effort       0.4775 Weighted catch/Sum of weights
           
Unweighted Catch 6 30 34 70  
Trips Interviewed 10 64 80 154  
Unweighted Catch per Effort       0.4545 Total catch/Trips interviewed
Back to top

More Information

Back to top