Time series of population density are commonly collected, and their statistical analysis plays an important role in ecological studies. Despite the importance, inferring population processes from time series remains challenging. Here, we apply co-integration analyses, which account for non-stationarity in time series, to the catch per unit effort of five populations (southern flounder, Paralichthys lethostigma; spotted seatrout, Cynoscion nebulosus; red drum, Sciaenops ocellatus; brown shrimp, Farfantepenaeus aztecus; and white shrimp, Litopenaeus setiferus) obtained in six coastal bays in Texas, United States, to understand their potential interactions. The results suggest significant interactions between fish and shrimp in an intermediate time scale, but also suggest no significant interaction in a short time scale. These results suggest that the causes of short-term fluctuations are not shared by shrimp and fish populations. However, the significant associations in the intermediate time scale may be a result of predator-prey interactions. If so, the results suggest slow response of fish populations to its prey (i.e. high inertia).